Skip to content

Baseline tagger: support constrained decoding? #5

Description

@nschneid

With the CMU Twitter dataset (Tweebank), some kinds of MWEs are already annotated. It would be nice to either (i) choose supersenses subject to the annotated MWE segmentation, or (ii) choose the segmentation and supersenses such that the annotated MWEs, at minimum, are present (additional MWEs may be predicted).

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions